chore(sync): update NanoGPT model catalog

providers/nano-gpt/models/Baichuan-M2.toml

@@ -1,5 +1,6 @@
 name = "Baichuan M2 32B Medical"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "baichuan"
 release_date = "2025-08-19"
 last_updated = "2025-08-19"
 attachment = false
@@ -11,6 +12,7 @@ open_weights = false
 [cost]
 input = 15.73
 output = 15.73
+cache_read = 7.865
 
 [limit]
 context = 32_768

providers/nano-gpt/models/Baichuan4-Air.toml

@@ -1,5 +1,6 @@
 name = "Baichuan 4 Air"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "baichuan"
 release_date = "2025-08-19"
 last_updated = "2025-08-19"
 attachment = false
@@ -11,6 +12,7 @@ open_weights = false
 [cost]
 input = 0.157
 output = 0.157
+cache_read = 0.0785
 
 [limit]
 context = 32_768

providers/nano-gpt/models/Baichuan4-Turbo.toml

@@ -1,5 +1,6 @@
 name = "Baichuan 4 Turbo"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "baichuan"
 release_date = "2025-08-19"
 last_updated = "2025-08-19"
 attachment = false
@@ -11,6 +12,7 @@ open_weights = false
 [cost]
 input = 2.42
 output = 2.42
+cache_read = 1.21
 
 [limit]
 context = 128_000

providers/nano-gpt/models/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond.toml

@@ -7,11 +7,12 @@ attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.49299999999999994
-output = 0.49299999999999994
+input = 0.493
+output = 0.493
+cache_read = 0.2465
 
 [limit]
 context = 16_384

providers/nano-gpt/models/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0.toml

@@ -7,11 +7,12 @@ attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
 input = 2.006
 output = 2.006
+cache_read = 1.003
 
 [limit]
 context = 16_384

providers/nano-gpt/models/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1.toml

@@ -7,11 +7,12 @@ attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
 input = 2.006
 output = 2.006
+cache_read = 1.003
 
 [limit]
 context = 16_384

providers/nano-gpt/models/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2.toml

@@ -7,11 +7,12 @@ attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.7989999999999999
-output = 0.7989999999999999
+input = 0.799
+output = 0.799
+cache_read = 0.3995
 
 [limit]
 context = 16_384

providers/nano-gpt/models/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2.toml

@@ -7,11 +7,12 @@ attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.7989999999999999
-output = 0.7989999999999999
+input = 0.799
+output = 0.799
+cache_read = 0.3995
 
 [limit]
 context = 16_384

providers/nano-gpt/models/Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B.toml

@@ -1,17 +1,18 @@
 name = "Llama 3.05 Storybreaker Ministral 70b"
 description = "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads"
 family = "llama"
-release_date = "2024-12-01"
+release_date = "2024-01-01"
 last_updated = "2024-12-01"
 attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.49299999999999994
-output = 0.49299999999999994
+input = 0.493
+output = 0.493
+cache_read = 0.2465
 
 [limit]
 context = 16_384

providers/nano-gpt/models/Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B.toml

@@ -1,17 +1,18 @@
 name = "Nemotron Tenyxchat Storybreaker 70b"
 description = "Nemotron model for efficient reasoning, coding, and specialized AI agents"
 family = "nemotron"
-release_date = "2024-12-01"
+release_date = "2024-01-01"
 last_updated = "2024-12-01"
 attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.49299999999999994
-output = 0.49299999999999994
+input = 0.493
+output = 0.493
+cache_read = 0.2465
 
 [limit]
 context = 16_384

providers/nano-gpt/models/GLM-4.6-Derestricted-v5.toml

@@ -1,16 +1,19 @@
 name = "GLM 4.6 Derestricted v5"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "glm"
 release_date = "2025-12-23"
 last_updated = "2025-12-23"
 attachment = false
-reasoning = false
+reasoning = true
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
+reasoning_options = []
 
 [cost]
 input = 0.4
 output = 1.5
+cache_read = 0.2
 
 [limit]
 context = 131_072

providers/nano-gpt/models/GalrionSoftworks/MN-LooseCannon-12B-v1.toml

@@ -1,17 +1,18 @@
 name = "MN-LooseCannon-12B-v1"
 description = "Mistral model for multilingual chat, reasoning, and tool-assisted workflows"
 family = "mistral-nemo"
-release_date = "2024-07-01"
+release_date = "2024-01-01"
 last_updated = "2024-07-01"
 attachment = false
 reasoning = false
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
 
 [cost]
-input = 0.49299999999999994
-output = 0.49299999999999994
+input = 0.493
+output = 0.493
+cache_read = 0.2465
 
 [limit]
 context = 16_384

providers/nano-gpt/models/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled.toml

@@ -1,25 +1,26 @@
 # Included in subscription
 name = "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled"
 description = "O-series reasoning model for hard analysis, math, coding, and planning"
+family = "claude"
 release_date = "2026-05-01"
 last_updated = "2026-05-01"
 attachment = true
 reasoning = true
-reasoning_options = []
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
+reasoning_options = []
 
 [cost]
 input = 0.306
 output = 0.306
 cache_read = 0.0306
 
 [limit]
-context = 262144
-input = 262144
-output = 16384
+context = 262_144
+input = 262_144
+output = 16_384
 
 [modalities]
-input = ["text", "image", "video"]
+input = ["text", "image"]
 output = ["text"]

providers/nano-gpt/models/Gemma-4-31B-Cognitive-Unshackled.toml

@@ -1,24 +1,28 @@
 # Included in subscription
 name = "Gemma 4 31B Cognitive Unshackled"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "gemma"
 release_date = "2026-05-01"
 last_updated = "2026-05-01"
 attachment = true
 reasoning = true
-reasoning_options = [{ type = "toggle" }]
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
+
+[[reasoning_options]]
+type = "toggle"
 
 [cost]
 input = 0.306
 output = 0.306
+cache_read = 0.153
 
 [limit]
-context = 262144
-input = 262144
-output = 16384
+context = 262_144
+input = 262_144
+output = 16_384
 
 [modalities]
-input = ["text", "image", "video"]
+input = ["text", "image"]
 output = ["text"]

providers/nano-gpt/models/Gemma-4-31B-DarkIdol.toml

@@ -1,24 +1,28 @@
 # Included in subscription
 name = "Gemma 4 31B DarkIdol"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "gemma"
 release_date = "2026-05-01"
 last_updated = "2026-05-01"
 attachment = true
 reasoning = true
-reasoning_options = [{ type = "toggle" }]
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
+
+[[reasoning_options]]
+type = "toggle"
 
 [cost]
 input = 0.306
 output = 0.306
+cache_read = 0.153
 
 [limit]
-context = 262144
-input = 262144
-output = 16384
+context = 262_144
+input = 262_144
+output = 16_384
 
 [modalities]
-input = ["text", "image", "video"]
+input = ["text", "image"]
 output = ["text"]

providers/nano-gpt/models/Gemma-4-31B-GarnetV2.toml

@@ -1,24 +1,28 @@
 # Included in subscription
 name = "Gemma 4 31B Garnet V2"
 description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "gemma"
 release_date = "2026-05-01"
 last_updated = "2026-05-01"
 attachment = true
 reasoning = true
-reasoning_options = [{ type = "toggle" }]
 tool_call = false
 structured_output = false
-open_weights = false
+open_weights = true
+
+[[reasoning_options]]
+type = "toggle"
 
 [cost]
 input = 0.306
 output = 0.306
+cache_read = 0.153
 
 [limit]
-context = 262144
-input = 262144
-output = 16384
+context = 262_144
+input = 262_144
+output = 16_384
 
 [modalities]
-input = ["text", "image", "video"]
+input = ["text", "image"]
 output = ["text"]